Let's fine-tune OpenAI gpt-oss (100% locally):

Build human-like memory for your Agents (open-source)! Every agentic and RAG system struggles with real-time knowledge updates and fast data retrieval. Zep solves these issues with its continuously evolving and temporally-aware Knowledge Graph. Like humans, Zep organizes an Agent's memories into episodes, extracts entities and their relationships from these episodes, and stores them in a knowledge graph: (refer to the image below as you read) 1) Episode Subgraph: Captures raw data with timestamps, retaining every detail for easy historical lookup. 2) Semantic Entity Subgraph: Extracts entities (e.g., “Alice,” “Google”) and facts (“Alice works at Google”). Everything is versioned, so outdated info gets replaced. 3) Community Subgraph: Groups related entities into clusters, with summaries for faster retrieval. Zep delivers up to 18.5% higher accuracy with 90% lower latency when compared to tools like MemGPT. It's fully open-source!

Enterprises build RAG over 100s of data sources, not one! - Microsoft ships it in M365 products. - Google ships it in its Vertex AI Search. - AWS ships it in its Amazon Q Business. Let's build an MCP-powered RAG over 200+ sources (100% local):

12 MCP, RAG, and Agents cheat sheets for AI engineers (with visuals):

Evaluate conversational LLM apps like ChatGPT in 3 steps (open-source). Unlike single-turn tasks, conversations unfold over multiple messages. This means that the LLM's behavior must be consistent, compliant, and context-aware across turns, not just accurate in one-shot output. In DeepEval, you can do that with just 3 steps: 1) Define your multi-turn test case as a ConversationalTestCase. 2) Define a metric with ConversationalGEval in plain English. 3) Run the evaluation. Done! This will provide a detailed breakdown of which conversations passed and which failed, along with a score distribution. Moreover, you also get a full UI to inspect individual turns. There are two good things about this: - The entire pipeline is extremely simple to set up and requires just a few lines of code. - DeepEval is 100% open-source with ~10k stars, and you can easily self-host it so your data stays where you want. Find the repo in the comments!

I built a RAG system that queries 36M+ vectors in <0.03 seconds. The technique used makes RAG 32x memory efficient! Check the detailed breakdown with code below:

- Google Maps uses graph ML to predict ETA - Netflix uses graph ML (GNN) in recommendation - Spotify uses graph ML (HGNNs) in recommendation - Pinterest uses graph ML (PingSage) in recommendation Here are 6 must-know ways for graph feature engineering (with code):

I have been using Jupyter Notebooks for over 9 years now. Here are 5 hidden features I discovered that most users aren't aware of:

The missing backend for your AI Agents! Motia is a unified system where APIs, background jobs, events, and agents are just plug-and-play steps. - Python, JS & TypeScript in the same workflow - Built-in observability - One-click deploy 100% open-source.

An MCP server that makes anyone a database engineer (open-source)! @MongoDB just released an MCP Server that lets AI tools like Claude, Cursor, and GitHub Copilot talk directly to a MongoDB deployment. That means anyone (technical or non-technical) can now say: - “Show me the most active users” - “Create a new database user with read-only access” - “What’s the schema for my orders collection?” ...and let the Agent handle the rest. No need to type in manual queries or memorize syntax. This MCP server works across: - Atlas - Community Edition - Enterprise Advanced English is all you need now to write production-grade queries. 100% open-source! Link in the next tweet. Thanks to the #MongoDB team for partnering today!